Chen-Chou Lo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chen-Chou Lo has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Hao Luo
Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan
1 shared publication - Hsin-Min Wang
Institute of Information Science, Academia Sinica, Taipei, Taiwan
1 shared publication - Hsin-Te Hwang
Institute of Information Science Academia Sinica Taiwan
1 shared publication - Wen-Chin Huang
Graduate School of Informatics, Nagoya University, Nagoya, Japan
1 shared publication - Yu Tsao
Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan
1 shared publication - Yu-Huai Peng
Institute of Information Science, Academia Sinica, Taipei, Taiwan
1 shared publication
Latest Publications
- Open Access
- 6 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 4 (4) , 468-479
Unsupervised Representation Disentanglement Using Cross Domain Features and Adversarial Learning in Variational Autoencoder Based Voice Conversion
An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this principle. In our prior work, we proposed a cross-domain VAE-VC (CDVAE-VC) framework, which utilized acoustic features of different properties, to improve the performance of VAE-VC. We believed that the success came from more disentangled latent representations. In this article, we extend the CDVAE-VC framework by incorporating the concept of adversarial learning, in order to further increase the degree of disentanglement, thereby improving the quality and similarity of converted speech. More specifically, we first investigate the effectiveness of incorporating the generative adversarial networks (GANs) with CDVAE-VC. Then, we consider the concept of domain adversarial training and add an explicit constraint to the latent representation, realized by a speaker classifier, to explicitly eliminate the speaker information that resides in the latent code. Experimental results confirm that the degree of disentanglement of the learned latent representation can be enhanced by both GANs and the speaker classifier. Meanwhile, subjective evaluation results in terms of quality and similarity scores demonstrate the effectiveness of our proposed methods.
- 6 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 4 (4) , 468-479
Open AccessUnsupervised Representation Disentanglement Using Cross Domain Features and Adversarial Learning in Variational Autoencoder Based Voice Conversion
An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this principle. In our prior work, we proposed a cross-domain VAE-VC (CDVAE-VC) framework, which utilized acoustic features of different properties, to improve the performance of VAE-VC. We believed that the success came from more disentangled latent representations. In this article, we extend the CDVAE-VC framework by incorporating the concept of adversarial learning, in order to further increase the degree of disentanglement, thereby improving the quality and similarity of converted speech. More specifically, we first investigate the effectiveness of incorporating the generative adversarial networks (GANs) with CDVAE-VC. Then, we consider the concept of domain adversarial training and add an explicit constraint to the latent representation, realized by a speaker classifier, to explicitly eliminate the speaker information that resides in the latent code. Experimental results confirm that the degree of disentanglement of the learned latent representation can be enhanced by both GANs and the speaker classifier. Meanwhile, subjective evaluation results in terms of quality and similarity scores demonstrate the effectiveness of our proposed methods.